INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.09

2:0.08

3:0.09

4:0.07

5:0.07

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 Pastebin

-2.10

nels

-1.78

cake

-1.69

Daddy

-1.65

enstein

-1.63

OVA

-1.60

 cleaners

-1.60

lux

-1.60

 Corona

-1.59

 Wonderland

-1.56

POSITIVE LOGITS

osponsors

1.95

ospons

1.92

ensional

1.72

pse

1.67

NF

1.63

 coales

1.58

 lamb

1.57

 startled

1.54

 trou

1.48

 kins

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.